Chenyang Lei
雷晨阳
Technical Lead, Unified Multimodal Understanding and Generation
Huawei · Celia Lab
Chenyang Lei is interested in helping humanity through AI. He is currently a Researcher at Huawei.
Chenyang Lei is the Technical Lead for "Unified Multimodal Understanding and Generation" at Huawei's Leibniz Institute, Celia Lab, and the technical owner of the Celia Image Editor (小艺修图), a key feature of the Mate 80 Pro. He was previously an Assistant Professor at the Centre for Artificial Intelligence and Robotics (CAIR), Chinese Academy of Sciences, and a Visiting Scholar at Princeton University, where he worked with Felix Heide. He received his Ph.D. in Computer Science from the Hong Kong University of Science and Technology (HKUST) under the supervision of Qifeng Chen, and his Bachelor's degree from Zhejiang University in 2018. He has also been a research intern at MSRA, NVIDIA, and SenseTime.
News
- Jun 2026 — Boogu-Image-0.1 is released!
- Nov 2025 — The Celia Image Editor (小艺修图) was showcased as a key highlight at the Huawei Mate 80 Pro launch event, and has since served over 100,000,000 uses.
- May 2025 — Joined Huawei's Celia Lab as Technical Lead for "Unified Multimodal Understanding and Generation"; technical owner of the Celia Image Editor (小艺修图).
- Sep 2022 — Joined Princeton University as a research scholar, working with Felix Heide.
- Sep 2022 — Joined CAIR, HKISI-CAS as an assistant professor.
- Aug 2022 — Passed my Ph.D. defense at HKUST.
- Mar 2019 — My first paper, "Fully Automatic Video Colorization with Self Regularization and Diversity", accepted to CVPR 2019.
- Aug 2018 — Started my Ph.D. in Computer Science at HKUST, advised by Qifeng Chen.
Research
I am interested in exploring system designs of visual computing pipelines, from advanced sensing technologies to more capable artificial intelligence. My current research topics include:
- Omni-Modality Beyond audio, vision, and language — toward a unified treatment of all physical signals.
- Unified Multimodal Understanding and Generation Building a single system that both understands and generates.
- AI-Native Hardware Designing everything — mechanical structure, sensors, and the product itself — for AI from the ground up.
Experience
- Huawei, Celia Lab — Technical Lead, "Unified Multimodal Understanding and Generation" 2025 – present Project Lead of Boogu, an open effort toward unified multimodal image understanding and generation. Technical owner of the Celia Image Editor (小艺修图), a key feature of the Mate 80 Pro.
- CAIR, HKISI, Chinese Academy of Sciences — Assistant Professor 2022 – 2025
- Princeton University — Visiting Scholar 2022 – 2024
- HKUST — Ph.D. in Computer Science Aug 2018 – 2022 Advised by Qifeng Chen.
- NVIDIA — Research Intern 2022
- Microsoft Research Asia (MSRA) — Research Intern 2021 – 2022
- SenseTime — Research Intern 2019 – 2020
- Zhejiang University — B.Eng. 2014 – 2018
Honors & Awards
- RedBird PhD Scholarship, HKUST 2021
- SENG Academic Award for Continuing PhD Students, HKUST 2020
- National Scholarship 2017
- Outstanding Graduate, Zhejiang University 2018
- Texas Instruments Scholarship 2017
- First-Class Scholarship for Outstanding Merits 2017
- Excellent Student Award 2016, 2017